|Publication number||US7624384 B2|
|Application number||US 10/999,115|
|Publication date||Nov 24, 2009|
|Filing date||Nov 30, 2004|
|Priority date||Nov 30, 2004|
|Also published as||US20060114132|
|Publication number||10999115, 999115, US 7624384 B2, US 7624384B2, US-B2-7624384, US7624384 B2, US7624384B2|
|Inventors||Peng Zhang, Jianhui Li, Alex Skaletsky, Orna Etzion|
|Original Assignee||Intel Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (19), Referenced by (15), Classifications (6), Legal Events (2)|
|External Links: USPTO, USPTO Assignment, Espacenet|
A dynamic binary translator is a real time compiler that translates a source binary code complying with the architecture of a source processor (“source architecture”) into a target binary code complying with the architecture of a target processor (“target architecture”). The translation process takes place during execution of the source binary code. In order to improve execution speed of the source binary code, the dynamic binary translator may need to reduce overhead during the translation process. Overhead may include, for example, repetitive translation of a same fragment or same set of instructions of the source binary code, redundancy in saving a same set of instructions or same fragment of the source binary code being translated, etc.
Reusing translated target binary code, commonly referred to as “translation reuse”, may be an effective way to reduce the overhead incurred by the dynamic binary translator. For example, if the source binary code is unchanged during execution, the relating translated target binary code may be reused. Translation reuse may require verifying consistency of the source instruction to be currently translated compared to previously translated source instruction relating to the target binary code to be reused. To ensure consistency, a no-fault verification method may require saving all the fragments of the source binary code that affect the translation, and comparing all the saved fragments with a fragment to be executed. Unfortunately, “blindly” saving and comparing all the fragments of the source binary code may be highly space and time consuming, and even impossible. In addition, because a dynamic binary translator may not be able to discover the exact boundaries of functions of the source binary code, a conventional dynamic binary translator may need to rely on an inaccurate verification procedure to verify consistency of the source binary code, leaving certain functional issues unresolved.
The invention will be understood and appreciated more fully from the following detailed description of embodiments of the invention, taken in conjunction with the accompanying drawings of which:
It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity.
In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the invention. However it will be understood by those of ordinary skill in the art that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods and procedures have not been described in detail so as not to obscure the embodiments of the invention.
Some portions of the detailed description in the following are presented in terms of algorithms and symbolic representations of operations on data bits or binary digital signals within a computer memory. These algorithmic descriptions and representations may be the techniques used by those skilled in the data processing arts to convey the substance of their work to others skilled in the art.
An algorithm is here, and generally, considered to be a self-consistent sequence of acts or operations leading to a desired result. These include physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers or the like. It should be understood, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities.
Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as “processing,” “computing,” “calculating,” “determining,” or the like, refer to the action and/or processes of a computer or computing system, or similar electronic computing device, that manipulate and/or transform data represented as physical, such as electronic, quantities within the computing system's registers and/or memories into other data similarly represented as physical quantities within the computing system's memories, registers or other such information storage, transmission or display devices.
Some embodiments of the invention may be implemented, for example, using a machine-readable medium or article which may store an instruction or a set of instructions that, if executed by a machine, cause the machine to perform a method and/or operations in accordance with embodiments of the invention. Such machine may include, for example, any suitable processing platform, computing platform, computing device, processing device, computing system, processing system, computer, processor, or the like, and may be implemented using any suitable combination of hardware and/or software. The machine-readable medium or article may include, for example, any suitable type of memory unit, memory device, memory article, memory medium, storage device, storage article, storage medium and/or storage unit, e.g., memory, removable or non-removable media, erasable or non-erasable media, writeable or re-writeable media, digital or analog media, hard disk, floppy disk, Compact Disk Read Only Memory (CD-ROM), Compact Disk Recordable (CD-R), Compact Disk Rewriteable (CD-RW), optical disk, magnetic media, various types of Digital Versatile Disks (DVDs), a tape, a cassette, or the like. The instructions may include any suitable type of code, for example, source code, compiled code, interpreted code, executable code, static code, dynamic code, or the like, and may be implemented using any suitable high-level, low-level, object-oriented, visual, compiled and/or interpreted programming language, e.g., C, C++, Java, BASIC, Pascal, Fortran, Cobol, assembly language, machine code, or the like.
Embodiments of the invention may include apparatuses for performing the operations herein. These apparatuses may be specially constructed for the desired purposes, or they may include a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer readable storage medium, such as, but is not limited to, any type of disk including floppy disks, optical disks, CD-ROMs, magnetic-optical disks, read-only memories (ROM), random access memories (RAM), electrically programmable read-only memories (EPROM), electrically erasable and programmable read only memories (EEPROM), magnetic or optical cards, or any other type of media suitable for storing electronic instructions, and capable of being coupled to a computer system bus.
The processes and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct a more specialized apparatus to perform the desired method. The desired structure for a variety of these systems will appear from the description below. In addition, embodiments of the invention are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the invention as described herein.
In the following description, various figures, diagrams, flowcharts, models, and descriptions are presented as different means to effectively convey the substances and illustrate different embodiments of the invention that are proposed in this application. It shall be understood by those skilled in the art that they are provided merely as exemplary samples, and shall not be constructed as limitation to the invention.
A non-exhaustive list of examples for apparatus 2 may include a desktop personal computer, a workstation, a server computer, a laptop computer, a notebook computer, a hand-held computer, a personal digital assistant (PDA), a mobile telephone, a game console, and the like.
A non-exhaustive list of examples for processor 4 may include a central processing unit (CPU), a digital signal processor (DSP), a reduced instruction set computer (RISC), a complex instruction set computer (CISC) and the like. Moreover, processor 4 may be part of an application specific integrated circuit (ASIC), or may be part of an application specific standard product (ASSP).
A non-exhaustive list of examples for memory 6 may include one or any combination of the following semiconductor devices, such as synchronous dynamic random access memory (SDRAM) devices, RAMBUS dynamic random access memory (RDRAM) devices, double data rate (DDR) memory devices, static random access memory (SRAM), flash memory devices, electrically erasable programmable read only memory devices (EEPROM), non-volatile random access memory devices (NVRAM), universal serial bus (USB) removable memory, and the like; optical devices, such as compact disk read only memory (CD ROM), and the like; and magnetic devices, such as a hard disk, a floppy disk, a magnetic tape, and the like. Memory 6 may be fixed within or removable from apparatus 2.
Source binary code 10, also referred to herein as source binaries, may comply with a source architecture, and a non-limiting example for the source architecture may include the Intel® architecture-32 (IA-32). Target binary code 20, also referred to herein as target binaries, may comply with a target architecture, and a non-limiting example for the target architecture may be the Intel® Itanium. If the source architecture does not comply with the target architecture, as is the case, for example, with the IA-32 and Itanium architectures, processor 4 may not be able to execute source binary code 10.
According to some exemplary embodiments of the invention, processor 4 may invoke dynamic binary translator 30 to translate source binary code 10 into target binary code 20. While fragments of source binary code 10 are being translated into code blocks of target binary code 20, processor 4 may execute the translated code blocks of target binary code 20. The results of executing the translated code blocks of target binaries 20 may generally correspond to the results of executing source binary code 10 on a processor that complies with the source architecture.
Dynamic binary translator 30 may translate source binaries 10 in fragments into code blocks of target binaries 20 for execution by a target processor complying with a target architecture. A source fragment, or code fragment, may be a source binary instruction, a basic instruction code, a code page, or other code size.
As shown in
Upon receiving the translation request, translation engine 32 may attempt to query for a previously translated code block that may potentially be reused to perform the instructions included in the source fragment. A potentially reusable code block may be a code block that has been previously translated from the same source fragment but may not be currently accessible by the execution engine 31. To search for such a potentially reusable code block, translation engine 32 may send a reuse request to reuse engine 33. If a potentially reusable translated code block is identified, reuse engine 33 may proceed to verify the consistency of the source fragment that corresponds to the identified code block, thereby to determine a reusability status of the identified code block. A source fragment is considered consistent if each and every instruction in the source fragment is exactly the same as it was before, for example, when the source fragment was originally translated. The reusable translated code block may then be passed to execution engine 31 for execution.
If the previously translated code block is determined to be unusable, e.g., because its corresponding source fragment has been changed or modified, or if no previously translated code block is found to be associated with, e.g., translated from, the source fragment to be currently translated, then translation engine 32 may translate the current source fragment and pass a newly translated code block to be executed by execution engine 31.
As shown in
A set of source fragments that are used in global optimization to translate and/or to optimize a translated code block may be referred to herein as the “Related Source Binaries” (RSB) of that translated code block. For example, as is shown in
It will be appreciated that if all source fragments in the RSB of a previously translated code block are consistent, that is, each and every instruction of the RSB source fragments is the same as it was before, e.g., when previously (e.g., most recently) translated, then the previously translated code block may be guaranteed to execute the correct instructions for the current source fragment. The translated code block may then be identified as safely reusable.
Therefore, according to exemplary embodiments of the present invention, verification of reusability status of a translated code block may be limited to verifying the consistency of only those source fragments that are related to the translated code block. Such source fragment verification, that is, verification of only the RSB elements of the translated code block, ensures correctness of the reused target code blocks and may be faster than conventional methods that verify the entire source binary code. Furthermore, it will be appreciated that verifying only the RSB elements of the translated code block, according to embodiments of the invention, does not compromise the quality of the translated target binaries.
The efficiency of source fragment verification for translation reuse may be measured by a parameter referred to herein as “Repeating Verification Ratio” (RVR). The RVR parameter may be defined as a ratio between the number of source fragments that are verified more than once, and the number of all verified source fragments. Additionally or alternatively, the efficiency of source fragment verification may be measured by a parameter referred to herein as “Needless Verification Ratio” (NVR). The NVR may be defined as a ratio between the number of source fragments that are verified but whose verification results are not actually used, and the total number of verified source fragments.
Verifying only the RSB elements of a translated code block, according to exemplary embodiments of the invention, may reduce the NVR of the translator and, thus, improve translation efficiency. However, it is appreciated that even if the NVR is minimal, the same source fragment may be verified more than once for different translated code blocks, because a given source fragment, e.g., source fragment 12, may relate to several translated code blocks, e.g., translated code blocks 21 and 22. This potential redundancy is overcome by some exemplary embodiments of the invention, e.g., by properly grouping the RSB elements of the translated code blocks, thereby further improving the translation efficiency in terms of the RVR parameter, as described in detail below.
According to exemplary embodiments of the invention, the efficiency of a dynamic binary translator, as measured by for example, RVR, may be improved by grouping translated code blocks into one or more code block groups, e.g., groups 26 and 27 as shown in
As shown in
In a RSB group such as, for example, source group 46, overlapping RSB elements, for example, source fragments 42 and 43, may be saved only once but may be referenced by multiple translated code blocks. In this manner, there may be less, or no duplicated RSB elements in any single group. The reusability status of a group to which a translated code block belongs may be used to determine the reusability status of the translated code block. If the group is marked as reusable, the code block may then be determined to be reusable. If the reusability status of the group is marked as unknown, reuse engine 33 may need to re-verify consistency of the group's RSB elements. If all of the RSB elements are verified to be consistent, the group may be re-marked as reusable, and the code block may be reused.
The process of grouping source fragments and verifying reusability of the group, according to embodiments of the invention, may result in a low, or even zero, RVR, a reduction in verification time, and conservation of storage space needed to contain the source fragments.
During execution of source binaries, execution engine 31 (
Upon receiving the translation request at box 412, translation engine 32 may send a reuse request to reuse engine 33 (
As indicated at box 416, reuse engine 33 may attempt to find or locate the previously translated code block, as described above, as well as a group to which the translated code block may belong. At box 418, if none of the translated code blocks is determined to meet the requirement of the reuse request, reuse engine 33 may send translation engine 32 an indication that a reusable translated code block for the source fragment cannot be found or located.
After receiving the indication at box 418 that no reusable translated code block can be found or located, at box 432 translation engine 32 may proceed to translate the source fragment. A newly translated code block may subsequently be generated and sent for execution by execution engine 31. More details concerning the translation process performed by translation engine 32 are described below with reference to
If a corresponding translated code block, e.g., code block 23 (
If a corresponding translated code block, e.g., code block 24 (
If at box 424 one or more of the RSB elements related to the group, e.g., group 27, are identified to be inconsistent, the group, e.g., group 27, may be considered non-reusable. In such a case, the group, e.g., group 27, may be deleted, as indicated at box 430, and all the translated code blocks in the group, including the identified code block 24, may be deemed to be non-reusable and be deleted. Reuse engine 33 may then send translation engine 32 an indication that a reusable translated code block has not been successfully located for the source fragment.
Translation engine 32 may then proceed to generate a new translated code block by translating the source fragment at box 432. The newly translated code block may then be passed for execution by execution engine 31. More details of the process of translating source fragments are described below.
When reuse engine 33 (
At box 516, translation engine 32 may verify elements, e.g., source fragments, of the newly created code block-C of base group-G against RSB elements, e.g., source fragments, of other groups of translated code blocks. If none of the RSB elements of base group-G is identified to intersect, or overlap, with RSB elements of the other groups, then base group-G may be categorized as a new group, and the marking of base group-G may remain as reusable. In this case, all of the RSB elements of code block-C are by default new to base group-G and are saved as a new RSB group, as indicated at box 522. The newly created code block-C may subsequently be passed for execution by execution engine 31, as indicated at box 524.
Alternatively, if one or more RSB elements of base group-G are found to intersect, or overlap, with one or more RSB elements of one of the existing groups, e.g., “group-O”, then at box 518 base group-G may be merged with group-O into form a new group, e.g., “group-N”. At box 520, the reusability status of group-N may be marked the same as that of group-O. Following the merging at box 522, any RSB elements of base group-G that do not intersect or overlap with RSB elements of group-O may be saved in group-N.
Alternatively, if one or more RSB elements of base group-G intersect, or overlap, with RSB elements of multiple groups of translated code blocks, the multiple groups may be merged together with base group-G at box 518 to form a new merged group, e.g., “group-M”. If the reusability status of one or more of the multiple groups is marked as unknown, group-M may also be marked as unknown. Otherwise, if all the merging groups are marked as reusable, group-M may be marked as reusable. At box 522, the RSB elements of base group-G that are not found in any of the merging groups may be added into group-M and may be saved in group-M. According to exemplary embodiments of the invention, RSB elements of all the merging groups that overlap with each other may only be saved once in group-M, such that no duplicated RSB element may be saved in group-M.
After merging base group-G with one or more groups of translated code blocks, code block-C of base group-G may subsequently be passed for execution by execution engine 31, as indicated at box 524.
As indicated at box 612, in some embodiments of the invention, during execution of the source binaries, a source fragment, e.g., a source instruction or a set of source instructions of any size, may be invalidated. Invalidation may be due to modules being unloaded, modified, or due to termination of a process and the likes. At box 614, translated code blocks that correspond to the invalidated source fragment may need to be invalidated and may be moved or copied to a separate group, e.g., invalidated binaries group 29 (
When a source fragment, for example, source fragment 45 (
In some cases, the reusability status of a group may be revived from unknown to reusable. This may be the case, for example, during verification of consistency of RSB elements at box 426 during execution of dynamic binary translation as described above with reference to
While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the spirit of the invention.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US5481712 *||Apr 6, 1993||Jan 2, 1996||Cognex Corporation||Method and apparatus for interactively generating a computer program for machine vision analysis of an object|
|US6330691 *||Feb 23, 1996||Dec 11, 2001||Institute For The Development Of Emerging Architectures Llc||Use of dynamic translation to provide breakpoints in non-writeable object code|
|US6463582 *||Oct 21, 1998||Oct 8, 2002||Fujitsu Limited||Dynamic optimizing object code translator for architecture emulation and dynamic optimizing object code translation method|
|US6523171 *||Nov 29, 1999||Feb 18, 2003||International Business Machines Corporation||Enhanced source code translator from procedural programming language (PPL) to an object oriented programming language (OOPL)|
|US6609248||Jun 30, 1999||Aug 19, 2003||Microsoft Corporation||Cross module representation of heterogeneous programs|
|US6694338 *||Aug 29, 2000||Feb 17, 2004||Contivo, Inc.||Virtual aggregate fields|
|US6704925 *||Dec 1, 1998||Mar 9, 2004||Vmware, Inc.||Dynamic binary translator with a system and method for updating and maintaining coherency of a translation cache|
|US6772413 *||Dec 8, 2000||Aug 3, 2004||Datapower Technology, Inc.||Method and apparatus of data exchange using runtime code generator and translator|
|US6820255 *||Apr 18, 2001||Nov 16, 2004||Elbrus International||Method for fast execution of translated binary code utilizing database cache for low-level code correspondence|
|US7000226 *||Jan 2, 2002||Feb 14, 2006||Intel Corporation||Exception masking in binary translation|
|US7017162 *||Jul 10, 2001||Mar 21, 2006||Microsoft Corporation||Application program interface for network software platform|
|US7065744 *||Jan 14, 2002||Jun 20, 2006||International Business Machines Corporation||System and method for converting management models to specific console interfaces|
|US7219335 *||Dec 8, 1999||May 15, 2007||Intel Corporation||Method and apparatus for stack emulation during binary translation|
|US7240326 *||Jan 14, 2002||Jul 3, 2007||International Business Machines Corporation||System and method for obtaining display names from management models|
|US7318216 *||Jun 17, 2004||Jan 8, 2008||Tablecode Software Corporation||Software application development environment facilitating development of a software application|
|US20020087954 *||Dec 29, 2000||Jul 4, 2002||Hong Wang||Quantization and compression for computation reuse|
|US20030088860 *||Nov 2, 2001||May 8, 2003||Fu-Hwa Wang||Compiler annotation for binary translation tools|
|US20050086648 *||Feb 13, 2004||Apr 21, 2005||Microsoft Corporation||Object-based systematic state space exploration of software|
|US20050120333 *||Oct 2, 2002||Jun 2, 2005||Katsuro Inoue||Software component importance evaluation system|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7770050||Apr 4, 2007||Aug 3, 2010||Sony Computer Entertainment Inc.||Method and apparatus for resolving clock management issues in emulation involving both interpreted and translated code|
|US7792666 *||Apr 4, 2007||Sep 7, 2010||Sony Computer Entertainment Inc.||Translation block invalidation prehints in emulation of a target system on a host system|
|US7813909||Apr 4, 2007||Oct 12, 2010||Sony Computer Entertainment Inc.||Register mapping in emulation of a target system on a host system|
|US7957952 *||Aug 12, 2010||Jun 7, 2011||Sony Computer Entertainment Inc.||Translation block invalidation prehints in emulation of a target system on a host system|
|US8060356||Dec 9, 2008||Nov 15, 2011||Sony Computer Entertainment Inc.||Processor emulation using fragment level translation|
|US8131535||Jun 3, 2011||Mar 6, 2012||Sony Computer Entertainment Inc.||Translation block invalidation prehints in emulation of a target system on a host system|
|US8234514||Jul 12, 2010||Jul 31, 2012||Sony Computer Entertainment Inc.||Method and apparatus for resolving clock management issues in emulation involving both interpreted and translated code|
|US8364461 *||Nov 9, 2009||Jan 29, 2013||International Business Machines Corporation||Reusing invalidated traces in a system emulator|
|US8392171||Aug 12, 2010||Mar 5, 2013||Sony Computer Entertainment Inc.||Register mapping in emulation of a target system on a host system|
|US8433555||Nov 14, 2011||Apr 30, 2013||Sony Computer Entertainment Inc.||Processor emulation using fragment level translation|
|US8515977||Sep 10, 2010||Aug 20, 2013||International Business Machines Corporation||Delta language translation|
|US8670973||Sep 16, 2010||Mar 11, 2014||International Business Machines Corporation||Language translation reuse in different systems|
|US20070261039 *||Apr 4, 2007||Nov 8, 2007||Sony Computer Entertainment Inc.||Translation block invalidation prehints in emulation of a target system on a host system|
|US20070277052 *||Apr 4, 2007||Nov 29, 2007||Sony Computer Entertainment Inc.||Method and apparatus for resolving clock management issues in emulation involving both interpreted and translated code|
|US20110112820 *||Nov 9, 2009||May 12, 2011||International Business Machines Corporation||Reusing Invalidated Traces in a System Emulator|
|U.S. Classification||717/136, 717/120|
|International Classification||G09F9/44, G09F9/45|
|Feb 16, 2005||AS||Assignment|
Owner name: INTEL CORPORATION, CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:ZHANG, PENG;LI, JIANHUI;SKALETSKY, ALEX;AND OTHERS;REEL/FRAME:015686/0526;SIGNING DATES FROM 20050105 TO 20050208
|Mar 8, 2013||FPAY||Fee payment|
Year of fee payment: 4